• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.633-636
• /
• 2021

개체명 인식은 주어진 문장 안의 고유한 의미가 있는 단어들을 인명, 지명, 단체명 등의 미리 정의된 개체의 범주로 분류하는 문제이다. 최근 연구에서는 딥 러닝, 대용량 언어 모델을 사용한 연구들이 활발하게 연구되어 높은 성능을 보이고 있다. 하지만 이러한 방법은 대용량 학습 말뭉치와 이를 처리할 수 있는 높은 연산 능력을 필요로 하며 모델의 실행 속도가 느려서 실용적으로 사용하기 어려운 문제가 있다. 본 논문에서는 얕은 기계 학습 기법을 적용한 ManiFL을 사용한 개체명 인식 시스템을 제안한다. 형태소의 음절, 품사 정보, 직전 형태소의 라벨만을 자질로 사용하여 실험하였다. 실험 결과 F1 score 기준 90.6%의 성능과 초당 974 문장을 처리하는 속도를 보였다.

• Journal of Korean language education
• /
• v.28 no.2
• /
• pp.113-153
• /
• 2017

This thesis is an analysis of research topics among doctorate research papers in Korean education from 1990 to 2016. The purpose of this paper is to keep up with current trends of Korean Language Education research in South Korea and China. The study aims to provide relevant information to researchers majoring in Korean language education and to determine future directions of Korean language education. In this study, among a total of 1709 Korean and Chinese studies of Korean language education, a final selection of 444 doctoral thesis (which consist of a total of 389 papers in Korea and a total of55 papers in China) were chosen from 1990 to 2016. The final selection of 444 papers was classified by year, topics and methodologies with a detailed analysis of the content. In addition, a detailed analysis of future directions and challenges for Korean education within South Korea and China is provided.

• Journal of Korean language education
• /
• v.29 no.4
• /
• pp.169-199
• /
• 2018

The purpose of this study is to examine Korean teachers' needs in in-service teacher training and variables related to their needs. This study was conducted with teachers from Korean language centers in Korean universities. The following three research questions were investigated: (1) What are the teachers' experiences of Korean language teaching and in-service teacher training? (2) What are the teachers' needs and expectations for the content and components of in-service education programs? Are there any disparity between teachers' needs and institutional needs? (3) What are the variables to be considered in designing an effective in-service teacher education program? In order to answer the research questions, a survey was developed and distributed to university Korean language institutions and Korean language teachers. The results indicated that both institutions and teachers are highly aware of the importance of the need for in-service teacher training. The results also suggested that a more teacher-centered, bottom-up approach should be implemented for successful outcomes of teacher education programs. Based on the results, this study offers a summary of the need for in-service teacher training and variables (both individual teacher variables and environmental variables) to be considered in designing the content and components of a teacher education program.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2005.06a
• /
• pp.1-16
• /
• 2005

• Journal of Korean language education
• /
• v.28 no.2
• /
• pp.155-184
• /
• 2017

As the media changes, communication patterns in modern society have been changed as well. This change in the media environment has also transformed the required literacy and it is time to accept this new literacy in Korean language education. At this point, this paper inspected the perception of media literacy classes of 73 teachers currently in the field of Korean language education. The results show that most teachers are aware of the media literacy which has changed socially, and show strong agreement that this changed literacy should be applied in the field of Korean language education. However, today's media literacy education is passive. Although teachers generally understand the dynamic features of newly emerging digital media, it remains as a tool in class. The teachers pointed out that device problems such as device environment and the spread of media are one of the many reasons for such passive usage. However, the more fundamental problem is that the new communication environment has not been reflected in the curriculum actively. Teachers thought that media literacy has a close relationship with Korean proficiency. Also, they saw that this kind of media literacy will be required for Korean learners in the future with more importance. Based on the results of the study, this paper argues that Korean language education needs to accept and reflect the changes of media in the curriculum.

• Language and Information
• /
• v.15 no.1
• /
• pp.31-62
• /
• 2011

TimeML is a markup language for events and temporal expressions in natural language, proposed in Pustejovsky et al. (2003) and latter standardized as ISO-TimeML (ISO 24617-1:2009). In this paper, we propose the further specification of ISO-TimeML for the Korean language with the concrete and thorough examination of real world texts. Since Korean differs significantly from English, which is the first and almost only extensively tested language with TimeML, one continuously run into theoretical and practical difficulties in the application of TimeML to Korean. We focus on the discussion for the consistent and efficient application of TimeML: how to consistently apply TimeML in accordance with Korean specificity and what to be annotated and what not to be, i.e. which information is meaningful in the temporal interpretation of Korean text, for efficient application of TimeML.

• Korean Journal of Human Ecology
• /
• v.21 no.3
• /
• pp.439-451
• /
• 2012

Maternal interaction behavior, language input and children's language of 34 multicultural families were compared with those of ordinary families. MLU's of multicultural mothers and their children were shorter than those of ordinary Korean mothers and children. Positive maternal interaction behaviors of multicultural mothers were significantly lower than those of ordinary mothers. Correlational analyses revealed that there were positive correlations among maternal interaction behaviors, mother's MLU and children' MLU in multicultural families. However, there were no such correlations in ordinary families. Findings suggest language education and support for multicultural mothers be an effective policy for their children's language development.

• Speech Sciences
• /
• v.10 no.3
• /
• pp.47-64
• /
• 2003

In the present study, the production of grammatical morphemes of Korean-speaking children with and without developmental language impairments was investigated. Ten children with language impairments (LI) (CA: 4; 4-6; 11, LA: 3; .6-5; 10) and 10 normal children (CA: 3;1-6;3, LA: 3;5-5;11) with matched language abilities participated in the study. Sixty pairs of pictures were used to elicit 12 types of predetermined grammatical morphemes. The two pictures of a pair were designed to elicit two sentences of the same sentence structure. After the investigator described one picture of a pair, the children were asked to describe the other picture. The LI children made more errors than the normal children in the production of 6 types of grammatical morphemes including: locative case marker, dative case marker, two connective endings of predicates representing cause and goal, and suffixes for passive and causative verbs. However, the LI children produced some grammatical morphemes as accurately as. the normal children. The two groups were similar in their error patterns. Some explanations for Korean-speaking LI children's use of grammatical morphemes were suggested.

• Journal of Platform Technology
• /
• v.12 no.1
• /
• pp.3-11
• /
• 2024

Deaf people who use sign language as their first language sometimes have difficulty communicating because they do not know spoken Korean. Deaf people are also members of society, so we must support to create a society where everyone can live together. In this paper, we present a method to increase the recognition rate of Korean sign language using a CNN model. When the original image was used as input to the CNN model, the accuracy was 0.96, and when the image corresponding to the skin area in the YCbCr color space was used as input, the accuracy was 0.72. It was confirmed that inserting the original image itself would lead to better results. In other studies, the accuracy of the combined Conv1d and LSTM model was 0.92, and the accuracy of the AlexNet model was 0.92. The CNN model proposed in this paper is 0.96 and is proven to be helpful in recognizing Korean sign language.

• Speech Sciences
• /
• v.15 no.1
• /
• pp.25-36
• /
• 2008

Language transfer means that the speaker's first language or previously acquired language influences on the production of the target language. This study aims at examining if there is native language influence on the production of English intonation by Korean speakers. The pitch accent patterns and the values of duration, F0, and intensity of the stressed vowel of the word with emphatic accent in the sentence produced by Korean speakers are compared to those of American English speakers. The results show that when the word receives emphatic accent in the sentence, American English speakers put H* accent on the stressed syllable of the word, but Korean speakers mostly assign high pitch on the last syllable of the word and have LH tonal pattern despite the fact that primary stress does not come on the last syllable within a word. In addition, comparison of the values of duration, F0, and intensity of the stressed vowel of the word with emphatic accent to those of the word with unmarked neutral accent shows that Korean speakers do not realize the intonation of the accented word appropriately because the values decrease even though the word has emphatic accent. This study finds out that there are differences in the production of English intonation of the word with emphatic accent between native speakers of English and Korean speakers, and that there is negative transfer of Korean intonation pattern to the production of English intonation by Korean speakers.